Performing data flow analysis in parallel

  • Authors:
  • Yong-fong Lee;Thomas J. Marlowe;Barbara G. Ryder

  • Affiliations:
  • Department of Computer Science and Center for Computer Aids for Industrial Productivity, Rutgers University;Department of Computer Science and Center for Computer Aids for Industrial Productivity, Rutgers University;Department of Computer Science and Center for Computer Aids for Industrial Productivity, Rutgers University

  • Venue:
  • Proceedings of the 1990 ACM/IEEE conference on Supercomputing
  • Year:
  • 1990

Quantified Score

Hi-index 0.00

Visualization

Abstract

We have designed a family of parallel data flow analysis algorithms for execution on a message-passing MIMD architecture, based on general-purpose, hybrid data flow analysis algorithms [22]. We have exploited the natural task partitioning of the hybrid algorithms and have explored a static mapping-dynamic scheduling strategy. Alternative mapping-scheduling choices and refinements of the flow graph condensation utilized are discussed. Our parallel hybrid algorithm family is illustrated on the Reaching Definitions problem, although parallel algorithms also exist for many interprocedural (e.g., Aliasing) and intraprocedural (e.g., Available Expressions) problems [20].